{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/coherence-evaluation","name":"Coherence Evaluation","slug":"coherence-evaluation","description_markdown":"Evaluating the overall coherence of text as measured by its readability and flow through ideas.","categories":[{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":28,"papers_with_code":15,"benchmarks":2,"benchmark_tables_in_archive":2,"benchmark_tables_shown":2,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":1,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/coherence-evaluation-on-gcdc-rst-accuracy","slug":"coherence-evaluation-on-gcdc-rst-accuracy","dataset":"GCDC + RST - Accuracy","dataset_url":"/dataset/gcdc","rows_in_archive":4,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"MTL with Transformer","paper_title":"Transformer Models for Text Coherence Assessment","paper_url":"/paper/transformer-models-for-text-coherence","paper_date":"2021-09-05","arxiv_id":"2109.02176","code_links":[{"title":"LiamMaclean216/Pytorch-Transfomer","url":"https://github.com/LiamMaclean216/Pytorch-Transfomer"},{"title":"tushar117/Transformer-Models-for-Text-Coherence-Assessment","url":"https://github.com/tushar117/Transformer-Models-for-Text-Coherence-Assessment"}],"syntology":null}},{"leaderboard":"/sota/coherence-evaluation-on-gcdc-rst-f1","slug":"coherence-evaluation-on-gcdc-rst-f1","dataset":"GCDC + RST - F1","dataset_url":"/dataset/gcdc","rows_in_archive":3,"metrics":["Average F1"],"first_row_in_archive_order":{"model":"RST-Ensemble","paper_title":"Neural RST-based Evaluation of Discourse Coherence","paper_url":"/paper/neural-rst-based-evaluation-of-discourse","paper_date":"2020-09-30","arxiv_id":"2009.14463","code_links":[{"title":"grig-guz/coherence-rst","url":"https://github.com/grig-guz/coherence-rst"}],"syntology":null}}],"datasets":[{"url":"/dataset/gcdc","name":"GCDC","full_name":"Grammarly Corpus of Discourse Coherence","num_papers_in_archive":13}],"subtasks":[],"parent_tasks":[{"url":"/task/text-classification","name":"Text Classification"}],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":1,"rows_per_page":100,"shown":28,"of":28,"of_with_code":15,"tagged_in_all":28,"counts":{"archive_papers_tagged":28,"with_a_code_link":15,"where_syntology_ran_a_sample":1,"not_listed_spam_title":0,"listed":28,"listed_where_code_ran":1,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":1,"listed_every_run_a_failure_of_syntologys_instrument":0,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/transformer-models-for-text-coherence","slug":"transformer-models-for-text-coherence","title":"Transformer Models for Text Coherence Assessment","date":"2021-09-05","arxiv_id":"2109.02176","repositories_listed":2,"syntology":null},{"url":"/paper/ecoh-turn-level-coherence-evaluation-for","slug":"ecoh-turn-level-coherence-evaluation-for","title":"ECoh: Turn-level Coherence Evaluation for Multilingual Dialogues","date":"2024-07-16","arxiv_id":"2407.11660","repositories_listed":1,"syntology":null},{"url":"/paper/couda-coherence-evaluation-via-unified-data","slug":"couda-coherence-evaluation-via-unified-data","title":"CoUDA: Coherence Evaluation via Unified Data Augmentation","date":"2024-03-31","arxiv_id":"2404.00681","repositories_listed":1,"syntology":null},{"url":"/paper/unlocking-structure-measuring-introducing-pdd","slug":"unlocking-structure-measuring-introducing-pdd","title":"Unlocking Structure Measuring: Introducing PDD, an Automatic Metric for Positional Discourse Coherence","date":"2024-02-15","arxiv_id":"2402.10175","repositories_listed":1,"syntology":null},{"url":"/paper/the-problem-of-coherence-in-natural-language","slug":"the-problem-of-coherence-in-natural-language","title":"The Problem of Coherence in Natural Language Explanations of Recommendations","date":"2023-12-18","arxiv_id":"2312.11356","repositories_listed":1,"syntology":null},{"url":"/paper/open-domain-text-evaluation-via-meta","slug":"open-domain-text-evaluation-via-meta","title":"Open-Domain Text Evaluation via Contrastive Distribution Methods","date":"2023-06-20","arxiv_id":"2306.11879","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/open-domain-text-evaluation-via-meta#ran","syntology_url":"https://syntology.ai/paper/2306.11879","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.11879"}},"official":{"repos":["pluslabnlp/cdm"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/transform-contrast-and-tell-coherent-entity","slug":"transform-contrast-and-tell-coherent-entity","title":"Transform, Contrast and Tell: Coherent Entity-Aware Multi-Image Captioning","date":"2023-02-04","arxiv_id":"2302.02124","repositories_listed":1,"syntology":null},{"url":"/paper/gispy-a-tool-for-measuring-gist-inference","slug":"gispy-a-tool-for-measuring-gist-inference","title":"GisPy: A Tool for Measuring Gist Inference Score in Text","date":"2022-05-25","arxiv_id":"2205.12484","repositories_listed":1,"syntology":null},{"url":"/paper/snac-coherence-error-detection-for-narrative","slug":"snac-coherence-error-detection-for-narrative","title":"SNaC: Coherence Error Detection for Narrative Summarization","date":"2022-05-19","arxiv_id":"2205.09641","repositories_listed":1,"syntology":null},{"url":"/paper/deam-dialogue-coherence-evaluation-using-amr","slug":"deam-dialogue-coherence-evaluation-using-amr","title":"DEAM: Dialogue Coherence Evaluation using AMR-based Semantic Manipulations","date":"2022-03-18","arxiv_id":"2203.09711","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/deam-dialogue-coherence-evaluation-using-amr#ran","syntology_url":"https://syntology.ai/paper/2203.09711","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.09711"}},"official":{"repos":["pluslabnlp/deam"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/a-neural-graph-based-local-coherence-model","slug":"a-neural-graph-based-local-coherence-model","title":"A Neural Graph-based Local Coherence Model","date":"2021-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/towards-quantifiable-dialogue-coherence","slug":"towards-quantifiable-dialogue-coherence","title":"Towards Quantifiable Dialogue Coherence Evaluation","date":"2021-06-01","arxiv_id":"2106.00507","repositories_listed":1,"syntology":null},{"url":"/paper/is-incoherence-surprising-targeted-evaluation","slug":"is-incoherence-surprising-targeted-evaluation","title":"Is Incoherence Surprising? Targeted Evaluation of Coherence Prediction from Language Models","date":"2021-05-07","arxiv_id":"2105.03495","repositories_listed":1,"syntology":null},{"url":"/paper/neural-rst-based-evaluation-of-discourse","slug":"neural-rst-based-evaluation-of-discourse","title":"Neural RST-based Evaluation of Discourse Coherence","date":"2020-09-30","arxiv_id":"2009.14463","repositories_listed":1,"syntology":null},{"url":"/paper/discourse-coherence-in-the-wild-a-dataset","slug":"discourse-coherence-in-the-wild-a-dataset","title":"Discourse Coherence in the Wild: A Dataset, Evaluation and Methods","date":"2018-05-14","arxiv_id":"1805.04993","repositories_listed":1,"syntology":null},{"url":null,"slug":"dial-in-llm-human-aligned-dialogue-intent","title":"Dial-In LLM: Human-Aligned LLM-in-the-loop Intent Clustering for Customer Service Dialogues","date":"2024-12-12","arxiv_id":"2412.09049","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-sequence-evaluation-based-on","title":"On the Sequence Evaluation based on Stochastic Processes","date":"2024-05-28","arxiv_id":"2405.17764","repositories_listed":0,"syntology":null},{"url":null,"slug":"bbscore-a-brownian-bridge-based-metric-for","title":"BBScore: A Brownian Bridge Based Metric for Assessing Text Coherence","date":"2023-12-28","arxiv_id":"2312.16893","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-the-generalization-ability-in-essay","title":"Improving the Generalization Ability in Essay Coherence Evaluation through Monotonic Constraints","date":"2023-07-25","arxiv_id":"2308.02506","repositories_listed":0,"syntology":null},{"url":"/paper/visual-writing-prompts-character-grounded","slug":"visual-writing-prompts-character-grounded","title":"Visual Writing Prompts: Character-Grounded Story Generation with Curated Image Sequences","date":"2023-01-20","arxiv_id":"2301.08571","repositories_listed":0,"syntology":null},{"url":null,"slug":"rethinking-self-supervision-objectives-for-1","title":"Rethinking Self-Supervision Objectives for Generalizable Coherence Modeling","date":"2021-10-14","arxiv_id":"2110.07198","repositories_listed":0,"syntology":null},{"url":null,"slug":"method-of-the-coherence-evaluation-of","title":"Method of the coherence evaluation of Ukrainian text","date":"2020-10-31","arxiv_id":"2011.00310","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-creation-of-a-corpus-for-coherence","title":"On the Creation of a Corpus for Coherence Evaluation of Discursive Units","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"which-evaluations-uncover-sense","title":"Which Evaluations Uncover Sense Representations that Actually Make Sense?","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"coheval-benchmarking-coherence-models","title":"Rethinking Coherence Modeling: Synthetic vs. Downstream Tasks","date":"2020-04-30","arxiv_id":"2004.14626","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-entity-driven-recursive-neural-network","title":"An entity-driven recursive neural network model for chinese discourse coherence modeling","date":"2017-04-14","arxiv_id":"1704.04336","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-sensitivity-of-topic-coherence-evaluation","title":"The Sensitivity of Topic Coherence Evaluation to Topic Cardinality","date":"2016-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"enriching-entity-grids-and-graphs-with","title":"Enriching entity grids and graphs with discourse relations: the impact in local coherence evaluation","date":"2015-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"syntology_records":2,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":1,"papers_placed":0,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[{"leaderboard":"/sota/coherence-evaluation-on-gcdc-rst-accuracy","since_archive":"/sota/coherence-evaluation-on-gcdc-rst-accuracy#since-judged","papers_judged":1,"placed":0},{"leaderboard":"/sota/coherence-evaluation-on-gcdc-rst-f1","since_archive":"/sota/coherence-evaluation-on-gcdc-rst-f1#since-judged","papers_judged":1,"placed":0}]},"papers_where_code_ran":1,"papers_where_code_ran_first_page":"/task/coherence-evaluation/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/task/coherence-evaluation/papers/ran/1","json":"/task/coherence-evaluation/papers/ran/1.json","rows":1}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"2a2f40e3634f4ead58b0f607b3027d4e84a43afea9a5763ad3a09b8542394540","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}